20,069 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.
Skill Claude Code
Full browser UAT for web apps — Playwright testing with console/network error capture, accessibility checks, i18n validation, and bug triage. Use when running screen-by-screen UAT or testing specific features in any web or hybrid app (React, Vue, Angular, Ionic, Next.js, etc).
Skill Claude CodeCodex
Shiplight QA toolkit — the single entry point for all Shiplight test/QA work. Use ONLY when the user explicitly says 'shiplight' (e.g. 'write a shiplight test', 'use shiplight to verify X', 'shiplight cover') or invokes /shiplight. Routes to subcommands: init, setup-test-auth, update, create-yaml-tests…
MCP server Claude CodeCodexCursor +2
QA-MCP: Test Standardization & Orchestration Server - MCP server for test case generation, quality control, and Xray integration. Runs locally from the qa-mcp Python package.
Skill Claude CodeCodex
Use when controlling a browser from the agent — daily tasks (open a site, fill a form, scrape), smoke-test after feature work, upload/download/dialogs. Prefer compact tools; never request screenshots unless a visual bug needs evidence.
MCP server Claude CodeCodexCursor +2
Automate Windows WPF apps from AI agents with semantic UIA selectors and FlaUI test generation. Runs locally from the @skuzadev/wpfpilot-mcp npm package.
MCP server Claude CodeCodexCursor +2
Independent, reproducible benchmark harness for agent-memory backends (MemPalace, Mem0, Zep/Graphiti, OpenViking): runs LongMemEval, LoCoMo, contradiction-detection, and a dozen other evals against all four and publishes the raw logs, not vendor-curated numbers. Runs locally from the memtrust-cli Python package.
Skill Claude CodeCodex
Lab playbook for the mcp-better server — claim equals wire; calls health and echo, and the optional confirmecho for MRTR. Use when connecting to mcp-better or testing its tools over protocol 2026-07-28.
MCP server Claude CodeCodexCursor +2
Find what broke in your agent calls. Pin it and CI stays red until you fix it. Local call forensics and regression guards for AI agents: turn timing, and whether the agent did what it said. Nothing leaves your machine. Runs locally from the hotato Python package.
Skill Claude CodeCodex
Complete reference for xcforge — 104 MCP tools (114 with the diagnose group) + 113 CLI commands for iOS development. Covers build, test, simulator, physical devices, SPM, UI automation, screenshots, logs, git, visual regression, accessibility, localization, session profiles, diagnosis workflows, plan execution, LLDB…
MCP server Claude CodeCodexCursor +2
Deterministic validation for AI-generated artifacts: JSON Schema, OpenAPI response, SQL syntax. Runs locally from the @machinegrade/validate npm package. Needs 2 environment variables to run.
Command Claude Code
Reusable prompt to activate agent 02-tdd-implementer. OJ-aware: advisory gate before handoff. Policy: .stackguide/oj.md.
Skill Claude CodeCodex
Behavioral verification intelligence for autonomous coding agents. Use this skill when the user asks "what could break in this PR?", "which workflows changed?", "what should I test before merging?", "is this change risky?", "what's the blast radius of removing this function?", or any question about understanding the…
Skill Claude Code
A guide for using the Xcelium simulator, a tool for testing digital hardware designs, including its commands and routing rules.
Plugin Claude Code
Bundles 7 skills, 3 agents, 1 hook · 869 tokens together
Agentic loop-engineering for complex tasks. PRD -> tagged phase plan -> autonomous TDD execution loop with deterministic escalation, command-based verification, and disk-backed state that survives compaction.
Skill Claude Code
MSW (Mock Service Worker) v2 and v3 best practices, patterns, and API guidance for API mocking in JavaScript/TypeScript tests and development. Covers handler design, server setup, response construction, testing patterns, GraphQL, and v1-to-v2 and v2-to-v3 migration. Baseline: msw ^3.0.0. Triggers on: msw imports…
imMamdouhaboammar/loop-engineering-skill
Skill Claude CodeCodex
Use when designing, orchestrating, or executing autonomous multi-agent coding loops with financial budget caps, minimal fixes, and continuous dev-QA gates.
Skill Claude CodeCodex
Test web applications in real browsers via Chrome DevTools Protocol including DOM inspection, console analysis, network profiling, performance auditing, Lighthouse CI, and visual regression.
Plugin Claude Code
Bundles 1 skill, 6 commands, 1 MCP server · 187 tokens together
Patent-pending agent-native software runtime for executing and verifying real application workflows. Drive browser interactions and E2E checks in plain English, enforce the VITRON-EA1 fail-closed safety gate, audit accessibility and security controls, and export signed evidence packs. Local-first, zero telemetry.
MCP server Claude CodeCodexCursor +2
Structural drift detection for nested JSON / dict data. Learn the shape of your payloads, freeze it as a contract, catch breaking changes before they hit your code. Runs locally from the contractguard Python package.
MCP server Claude CodeCodexCursor +2
MCP server for iOS Simulator automation — accessibility tree, screenshot, tap/swipe/type, and AI screen perception tools. Runs locally from the app-screen-mcp npm package.
MCP server Claude CodeCodexCursor +2
MCP server "testmo-mcp" as configured in strelec00/testmo-mcp. Runs locally from the testmo-mcp Python package.
MCP server Claude CodeCodexCursor +2
MCP server for MyCase API — full coverage for law firm practice management. Runs locally from the mycase-mcp Python package.
MCP server Claude CodeCodexCursor +2
MCP server for TLA+ toolchain (TLC, SANY, PlusCal, TLATeX). Runs locally from the @richashworth/tlaplus-mcp npm package.
Ravindrabisht12/axe-devtool-mcp
MCP server Claude CodeCodexCursor +2
MCP server that runs axe-core accessibility scans (via Playwright) on URLs and HTML, for use with Claude Code and other MCP clients. Runs locally from the axe-devtools-mcp npm package.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: